Triple

T14894366
Position Surface form Disambiguated ID Type / Status
Subject Sky Living E359831 entity
Predicate sisterChannel P5818 FINISHED
Object Sky Arts E72551 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Sky Arts | Statement: [Sky Living, sisterChannel, Sky Arts]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sky Arts
Context triple: [Sky Living, sisterChannel, Sky Arts]
  • A. Sky Arts chosen
    Sky Arts is a British pay television channel dedicated to arts and culture programming, including music, theatre, visual arts, and documentaries.
  • B. Sky TV
    Sky TV is a British subscription television service offering a wide range of satellite and streaming channels, on-demand content, and original programming.
  • C. Beeb
    Beeb is the popular nickname for the BBC Micro, an influential 1980s home computer widely used in UK education and early programming.
  • D. Anglia Television
    Anglia Television is a British regional television broadcaster best known for serving the East of England as part of the ITV network.
  • E. Channel 4
    Channel 4 is the on-air brand used by Pittsburgh television station WTAE-TV, an ABC-affiliated local broadcast outlet.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d827980cbc8190a0c569ae3940a1d9 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69ded5f9d10c819091732d7a5a42a682 completed April 15, 2026, 12:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe6b679fb081908cf8f41acfba3b99 completed May 8, 2026, 11:01 p.m.
Created at: April 10, 2026, 2:10 a.m.